"Fix" debug console, we were checking the cvar before any cvars were loaded, and the condition it checks in AttachConsole is somehow always false
Remove dead #if 0'd code in math.h On amd64, page_size == 4096 constant, on amd64 w/ win32, allocation_granularity == 65536. These values for x86 windows havent changed over the last 20 years so this is probably safe and gives a modest code size reduction Enable XE_USE_KUSER_SHARED. This sources host time from KUSER_SHARED instead of from QueryPerformanceCounter, which is far faster, but only has a granularity of 100 nanoseconds. In some games seemingly random crashes were happening that were hard to trace because the faulting thread was actually not the one that was misbehaving, another threads stack was underflowing into the faulting thread. Added a bunch of code to synchronize the guest stack and host stack so that if a guest longjmps the host's stack will be adjusted. Changes were also made to allow the guest to call into a piece of an existing x64 function. This synchronization might have a slight performance impact on lower end cpus, to disable it set enable_host_guest_stack_synchronization to false. It is possible it may have introduced regressions, but i dont know of any yet So far, i know the synchronization change fixes the "hub crash" in super sonic and allows the game "london 2012" to go ingame. Removed emit_useless_fpscr_updates, not emitting these updates breaks the raiden game MapGuestAddressToMachineCode now returns nullptr if no address was found, instead of the start of the function add Processor::LookupModule Add Backend::DeinitializeBackendContext Use WriteRegisterRangeFromRing_WithKnownBound<0, 0xFFFF> in WriteRegisterRangeFromRing for inlining (previously regressed on performance of ExecutePacketType0) add notes about flags that trap in XamInputGetCapabilities 0 == 3 in XamInputGetCapabilities Name arg 2 of XamInputSetState PrefetchW in critical section kernel funcs if available & doing cmpxchg Add terminated field to X_KTHREAD, set it on termination Expanded the logic of NtResumeThread/NtSuspendThread to include checking the type of the handle (in release, LookupObject doesnt seem to do anything with the type) and returning X_STATUS_OBJECT_TYPE_MISMATCH if invalid. Do termination check in NtSuspendThread. Add basic host exception messagebox, need to flesh it out more (maybe use the new stack tracking stuff if on guest thrd?) Add rdrand patching hack, mostly affects users with nvidia cards who have many threads on zen Use page_size_shift in more places Once again disable precompilation! Raiden is mostly weird ppc asm which probably breaks the precompilation. The code is still useful for running the compiler over the whole of an xex in debug to test for issues "Fix" debug console, we were checking the cvar before any cvars were loaded, and the condition it checks in AttachConsole is somehow always false Remove dead #if 0'd code in math.h On amd64, page_size == 4096 constant, on amd64 w/ win32, allocation_granularity == 65536. These values for x86 windows havent changed over the last 20 years so this is probably safe and gives a modest code size reduction Enable XE_USE_KUSER_SHARED. This sources host time from KUSER_SHARED instead of from QueryPerformanceCounter, which is far faster, but only has a granularity of 100 nanoseconds. In some games seemingly random crashes were happening that were hard to trace because the faulting thread was actually not the one that was misbehaving, another threads stack was underflowing into the faulting thread. Added a bunch of code to synchronize the guest stack and host stack so that if a guest longjmps the host's stack will be adjusted. Changes were also made to allow the guest to call into a piece of an existing x64 function. This synchronization might have a slight performance impact on lower end cpus, to disable it set enable_host_guest_stack_synchronization to false. It is possible it may have introduced regressions, but i dont know of any yet So far, i know the synchronization change fixes the "hub crash" in super sonic and allows the game "london 2012" to go ingame. Removed emit_useless_fpscr_updates, not emitting these updates breaks the raiden game MapGuestAddressToMachineCode now returns nullptr if no address was found, instead of the start of the function add Processor::LookupModule Add Backend::DeinitializeBackendContext Use WriteRegisterRangeFromRing_WithKnownBound<0, 0xFFFF> in WriteRegisterRangeFromRing for inlining (previously regressed on performance of ExecutePacketType0) add notes about flags that trap in XamInputGetCapabilities 0 == 3 in XamInputGetCapabilities Name arg 2 of XamInputSetState PrefetchW in critical section kernel funcs if available & doing cmpxchg Add terminated field to X_KTHREAD, set it on termination Expanded the logic of NtResumeThread/NtSuspendThread to include checking the type of the handle (in release, LookupObject doesnt seem to do anything with the type) and returning X_STATUS_OBJECT_TYPE_MISMATCH if invalid. Do termination check in NtSuspendThread. Add basic host exception messagebox, need to flesh it out more (maybe use the new stack tracking stuff if on guest thrd?) Add rdrand patching hack, mostly affects users with nvidia cards who have many threads on zen Use page_size_shift in more places Once again disable precompilation! Raiden is mostly weird ppc asm which probably breaks the precompilation. The code is still useful for running the compiler over the whole of an xex in debug to test for issues
This commit is contained in:
chss95cs@gmail.com
@@ -24,7 +24,8 @@
|
||||
#endif
|
||||
|
||||
DECLARE_int64(x64_extension_mask);
|
||||
|
||||
DECLARE_int64(max_stackpoints);
|
||||
DECLARE_bool(enable_host_guest_stack_synchronization);
|
||||
namespace xe {
|
||||
class Exception;
|
||||
} // namespace xe
|
||||
@@ -41,14 +42,25 @@ typedef void* (*HostToGuestThunk)(void* target, void* arg0, void* arg1);
|
||||
typedef void* (*GuestToHostThunk)(void* target, void* arg0, void* arg1);
|
||||
typedef void (*ResolveFunctionThunk)();
|
||||
|
||||
struct X64BackendStackpoint {
|
||||
uint64_t host_stack_;
|
||||
unsigned guest_stack_;
|
||||
// pad to 16 bytes so we never end up having a 64 bit load/store for
|
||||
// host_stack_ straddling two lines. Consider this field reserved for future
|
||||
// use
|
||||
unsigned unused_;
|
||||
};
|
||||
// located prior to the ctx register
|
||||
// some things it would be nice to have be per-emulator instance instead of per
|
||||
// context (somehow placing a global X64BackendCtx prior to membase, so we can
|
||||
// negatively index the membase reg)
|
||||
struct X64BackendContext {
|
||||
void* ResolveFunction_Ptr; // cached pointer to resolvefunction
|
||||
// guest_tick_count is used if inline_loadclock is used
|
||||
uint64_t* guest_tick_count;
|
||||
// records mapping of host_stack to guest_stack
|
||||
X64BackendStackpoint* stackpoints;
|
||||
|
||||
unsigned int current_stackpoint_depth;
|
||||
unsigned int mxcsr_fpu; // currently, the way we implement rounding mode
|
||||
// affects both vmx and the fpu
|
||||
unsigned int mxcsr_vmx;
|
||||
@@ -81,6 +93,19 @@ class X64Backend : public Backend {
|
||||
return resolve_function_thunk_;
|
||||
}
|
||||
|
||||
void* synchronize_guest_and_host_stack_helper() const {
|
||||
return synchronize_guest_and_host_stack_helper_;
|
||||
}
|
||||
void* synchronize_guest_and_host_stack_helper_for_size(size_t sz) const {
|
||||
switch (sz) {
|
||||
case 1:
|
||||
return synchronize_guest_and_host_stack_helper_size8_;
|
||||
case 2:
|
||||
return synchronize_guest_and_host_stack_helper_size16_;
|
||||
default:
|
||||
return synchronize_guest_and_host_stack_helper_size32_;
|
||||
}
|
||||
}
|
||||
bool Initialize(Processor* processor) override;
|
||||
|
||||
void CommitExecutableRange(uint32_t guest_low, uint32_t guest_high) override;
|
||||
@@ -97,7 +122,8 @@ class X64Backend : public Backend {
|
||||
void InstallBreakpoint(Breakpoint* breakpoint, Function* fn) override;
|
||||
void UninstallBreakpoint(Breakpoint* breakpoint) override;
|
||||
virtual void InitializeBackendContext(void* ctx) override;
|
||||
|
||||
virtual void DeinitializeBackendContext(void* ctx) override;
|
||||
virtual void PrepareForReentry(void* ctx) override;
|
||||
X64BackendContext* BackendContextForGuestContext(void* ctx) {
|
||||
return reinterpret_cast<X64BackendContext*>(
|
||||
reinterpret_cast<intptr_t>(ctx) - sizeof(X64BackendContext));
|
||||
@@ -120,7 +146,12 @@ class X64Backend : public Backend {
|
||||
HostToGuestThunk host_to_guest_thunk_;
|
||||
GuestToHostThunk guest_to_host_thunk_;
|
||||
ResolveFunctionThunk resolve_function_thunk_;
|
||||
void* synchronize_guest_and_host_stack_helper_ = nullptr;
|
||||
|
||||
// loads stack sizes 1 byte, 2 bytes or 4 bytes
|
||||
void* synchronize_guest_and_host_stack_helper_size8_ = nullptr;
|
||||
void* synchronize_guest_and_host_stack_helper_size16_ = nullptr;
|
||||
void* synchronize_guest_and_host_stack_helper_size32_ = nullptr;
|
||||
#if XE_X64_PROFILER_AVAILABLE == 1
|
||||
GuestProfilerData profiler_data_;
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user